Hearts Gym: Learning Reinforcement Learning as a Team Event

Jan Ebert, Danimir T. Doncevic, Ramona Kloß, Stefan Kesselheim
Proceedings of the Third Teaching Machine Learning and Artificial Intelligence Workshop, PMLR 207:16-21, 2023.

Abstract

Amidst the COVID-19 pandemic, the authors of this paper organized a Reinforcement Learning (RL) course for a graduate school in the field of data science. We describe the strategy and materials for creating an exciting learning experience despite the ubiquitous Zoom fatigue and evaluate the course qualitatively. The key organizational features are a focus on a competitive hands-on setting in teams supported by a minimum of lectures providing the essential background on RL. The practical part of the course revolved around Hearts Gym, an RL environment for the card game Hearts that we developed as an entry-level tutorial to RL. Participants were tasked with training agents to explore reward shaping and other RL hyperparameters. For a final evaluation, the agents of the participants competed against each other.

Cite this Paper


BibTeX
@InProceedings{pmlr-v207-ebert23a, title = {Hearts Gym: Learning Reinforcement Learning as a Team Event}, author = {Ebert, Jan and Doncevic, Danimir T. and Klo\ss, Ramona and Kesselheim, Stefan}, booktitle = {Proceedings of the Third Teaching Machine Learning and Artificial Intelligence Workshop}, pages = {16--21}, year = {2023}, editor = {Kinnaird, Katherine M. and Steinbach, Peter and Guhr, Oliver}, volume = {207}, series = {Proceedings of Machine Learning Research}, month = {19--23 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v207/ebert23a/ebert23a.pdf}, url = {https://proceedings.mlr.press/v207/ebert23a.html}, abstract = {Amidst the COVID-19 pandemic, the authors of this paper organized a Reinforcement Learning (RL) course for a graduate school in the field of data science. We describe the strategy and materials for creating an exciting learning experience despite the ubiquitous Zoom fatigue and evaluate the course qualitatively. The key organizational features are a focus on a competitive hands-on setting in teams supported by a minimum of lectures providing the essential background on RL. The practical part of the course revolved around Hearts Gym, an RL environment for the card game Hearts that we developed as an entry-level tutorial to RL. Participants were tasked with training agents to explore reward shaping and other RL hyperparameters. For a final evaluation, the agents of the participants competed against each other.} }
Endnote
%0 Conference Paper %T Hearts Gym: Learning Reinforcement Learning as a Team Event %A Jan Ebert %A Danimir T. Doncevic %A Ramona Kloß %A Stefan Kesselheim %B Proceedings of the Third Teaching Machine Learning and Artificial Intelligence Workshop %C Proceedings of Machine Learning Research %D 2023 %E Katherine M. Kinnaird %E Peter Steinbach %E Oliver Guhr %F pmlr-v207-ebert23a %I PMLR %P 16--21 %U https://proceedings.mlr.press/v207/ebert23a.html %V 207 %X Amidst the COVID-19 pandemic, the authors of this paper organized a Reinforcement Learning (RL) course for a graduate school in the field of data science. We describe the strategy and materials for creating an exciting learning experience despite the ubiquitous Zoom fatigue and evaluate the course qualitatively. The key organizational features are a focus on a competitive hands-on setting in teams supported by a minimum of lectures providing the essential background on RL. The practical part of the course revolved around Hearts Gym, an RL environment for the card game Hearts that we developed as an entry-level tutorial to RL. Participants were tasked with training agents to explore reward shaping and other RL hyperparameters. For a final evaluation, the agents of the participants competed against each other.
APA
Ebert, J., Doncevic, D.T., Kloß, R. & Kesselheim, S.. (2023). Hearts Gym: Learning Reinforcement Learning as a Team Event. Proceedings of the Third Teaching Machine Learning and Artificial Intelligence Workshop, in Proceedings of Machine Learning Research 207:16-21 Available from https://proceedings.mlr.press/v207/ebert23a.html.

Related Material